# Learned Non-Maximum Suppression for 3D Object Detection Source: [Learned Non-Maximum Suppression for 3D Object Detection]() Collection index: [llms.txt]() Data updated: 2026-06-04T05:01:01.134Z Authors: Timo Osterburg, Stefan Sch\\"utte, Torsten Bertram Published: 2026-06-02T12:34:14.000Z ## Abstract Post-processing is a critical stage in LiDAR-based 3D object detection, where dense and overlapping proposals must be filtered for compact and reliable perception. This work introduces two learned filtering modules that replace heuristic non-maximum suppression (NMS) by leveraging relations among detections. D2D-Rescore employs transformer-based detection-to-detection (D2D) attention, while GossipNet3D adapts the 2D GossipNet concept to 3D through localized message passing in bird's-eye view. A metric-aware matching strategy aligned with the nuScenes evaluation protocol ensures consistent training and validation behavior, improving overall detection performance. Both approaches improve mean average precision (mAP), nuScenes detection score (NDS), and true positive quality compared to CircleNMS, particularly for small and infrequent classes, while adding minimal computational overhead. These results demonstrate that learned, detection-level filtering can enhance 3D detector reliability without modifying the base network, offering a principled alternative to heuristic suppression. Code is available at https://github.com/rst-tu-dortmund/learned-3d-nms . ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [3D Object Detection on nuScenes (val) (Core Metrics)](): 3D Object Detection; nuScenes (val); NDS: 57.78. ## Original sources and implementation [Original paper]() [PDF]()